zju3dv / Vox-Fusion

Code for "Dense Tracking and Mapping with Voxel-based Neural Implicit Representation", ISMAR 2022

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FileNotFoundError: [Errno 2] No such file or directory [W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors] [W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]

antonpapa opened this issue · comments

insert keyframe
******* tracking process started! *******
tracking frame: 53%|██████████████████████████████████████████████████▍ | 52/99 [00:41<00:43, 1.07it/s]insert keyframe
********** current num kfs: 2 **********
tracking frame: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 99/99 [01:28<00:00, 1.12it/s]
========== stop_mapping set ==========
******* tracking process died *******
Process Process-2:
Traceback (most recent call last):
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/acc/Vox-Fusion/src/mapping.py", line 87, in spin
tracked_frame = kf_buffer.get()
^^^^^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/queues.py", line 122, in get
return _ForkingPickler.loads(res)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/site-packages/torch/multiprocessing/reductions.py", line 495, in rebuild_storage_fd
fd = df.detach()
^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/resource_sharer.py", line 57, in detach
with _resource_sharer.get_connection(self._id) as conn:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/resource_sharer.py", line 86, in get_connection
c = Client(address, authkey=process.current_process().authkey)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/connection.py", line 518, in Client
c = SocketClient(address)
^^^^^^^^^^^^^^^^^^^^^
File "/home/acc/anaconda3/envs/vox_fusion/lib/python3.11/multiprocessing/connection.py", line 646, in SocketClient
s.connect(address)
FileNotFoundError: [Errno 2] No such file or directory
[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
Hi,the same problem occurred in #49,and I have tried the method(modified line 83 of the src/mapping. py file "while True:" as "while len(self.keyframe_graph) < 40:"),but it doesn't work,does anyone knows the reason,tks.

OK guys,problem is solved,see the problem #23,bro got the same question ,code is ok,but my computer is too suck.If you guys have the same problem could try to make the end_frame: in yaml smaller,and the only problem is that I should get a better cpu and a better gpu (lol).